riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-02 03:01:07 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Added Mish Activation Function

Browse Source 
Mish is a new activation function proposed here - https://arxiv.org/abs/1908.08681
It has seen some recent success and has been adopted in SpaCy, Thic, TensorFlow Addons and FastAI-dev. 
All benchmarks recorded till now (including against ReLU, Swish and GELU) is present in the repository - https://github.com/digantamisra98/Mish
Might be a good addition to experiment with especially in the Bert Model.
This commit is contained in:
Diganta Misra 2019-11-07 03:45:43 +05:30 committed by GitHub
parent 1c542df7e5
commit 070dcf1c02
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
transformers/modeling_bert.py
View File

@ -138,7 +138,11 @@ def swish(x):
return x * torch.sigmoid(x)
ACT2FN = {"gelu": gelu, "relu": torch.nn.functional.relu, "swish": swish, "gelu_new": gelu_new}
def mish(x):
return x * torch.tanh(nn.functional.softplus(x))
ACT2FN = {"gelu": gelu, "relu": torch.nn.functional.relu, "swish": swish, "gelu_new": gelu_new, "mish": mish}
BertLayerNorm = torch.nn.LayerNorm